prior-auth-review-skill

anthropics/healthcareOfficial collectionCoding & code reviewSecurityScience & research

prior-auth-review-skill is a skill in anthropics/healthcare, last changed 15 Jun 2026. It can name web addresses and include files we can't read.

From the author
Automate payer review of prior authorization (PA) requests. This skill should be used when users say "Review this PA request", "Process prior authorization for [procedure]", "Assess medical necessity", "Generate PA decision", or when processing clinical documentation for coverage policy validation and authorization decisions.

At a glance

What it can touch

How much a skill can do, not whether it is risky.

Pattern check

6 items to review

Binary, compiled, archived or document file

R32 · High · assets/Medicare_PA_Approval_Letter.pdfand 5 more

Commit c7ed150 · 1 Nov 2026

How the check works

Pattern check:6 items to reviewSee them

Install

Each tab says whether it installs commit c7ed150, the one we checked, or the latest version.

Read these 6 items before installing, starting with Binary, compiled, archived or document file — assets/Medicare_PA_Approval_Letter.pdf

Read SKILL.md first
No licence
Licence
434
Repo stars
Publisher

What it can touch

From the files and frontmatter at commit c7ed150. This is how much a skill can do, not whether it is risky.

Pattern check

Pattern check: 6 items to review · commit c7ed150 · 1 Nov 2026

We checked every text file in this skill, at commit c7ed150 on 1 Nov 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check worksReport an incorrect finding

Files we didn't read

  • assets/Medicare_PA_Approval_Letter.pdf · document
  • assets/sample/01_Prior_Auth_Request_Form.pdf · document
  • assets/sample/02_Clinical_Notes_H_and_P.pdf · document
  • assets/sample/03_CT_Chest_Report.pdf · document
  • assets/sample/04_Laboratory_Results.pdf · document
  • assets/sample/05_Pulmonary_Function_Tests.pdf · document
  • https://www.cms.gov/medicare/physician-fee-schedule/search
  • https://www.cms.gov/medicare/coding-billing/national-correct-coding-initiative-ncci-edits
  • https://taxonomy.nucc.org/
  • https://www.cms.gov/medicare/physician-fee-schedule/search?Y=0&T=4&P=0&L=

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

  • Agent Skills specFails

    The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.

    • Error

      The name "prior-auth-review-skill" doesn't match its folder "prior-auth". The spec requires them to match. N4

      Fix: Set name: prior-auth, or rename the folder to prior-auth-review-skill.

    • Note

      There is no license field, so readers can't tell whether they may reuse the skill. O2

      Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.

    • Note

      Reference files that SKILL.md doesn't link: references/notification-letter-templates.md (linked only from references/02-decision-notification.md) and references/tools.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: references/01-intake-assessment.md (603 lines) and references/02-decision-notification.md (260 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • Claude CodePasses

    Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.

    • Note

      The name "prior-auth-review-skill" doesn't match its folder "prior-auth". Claude Code shows the skill as /prior-auth-review-skill, and the folder name also invokes it. N4

      Fix: Set name: prior-auth, or rename the folder to prior-auth-review-skill.

    • Note

      Reference files that SKILL.md doesn't link: references/notification-letter-templates.md (linked only from references/02-decision-notification.md) and references/tools.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: references/01-intake-assessment.md (603 lines) and references/02-decision-notification.md (260 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • Claude apps & API uploadFails

    Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.

    • Error

      The name "prior-auth-review-skill" doesn't match its folder "prior-auth". claude.ai refuses an upload whose folder name doesn't match the skill name. N4

      Fix: Set name: prior-auth, or rename the folder to prior-auth-review-skill.

    • Note

      The description is 327 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4

      Fix: If the claude.ai upload refuses it, trim the description to 200 characters.

    • Note

      Reference files that SKILL.md doesn't link: references/notification-letter-templates.md (linked only from references/02-decision-notification.md) and references/tools.md. Anthropic suggests linking every reference file directly from SKILL.md. B4

      Fix: Link each one from SKILL.md and say when to read it.

    • Note

      Reference files over 100 lines with no table of contents at the top: references/01-intake-assessment.md (603 lines) and references/02-decision-notification.md (260 lines). B5

      Fix: Add a short list of the sections at the top of each.

  • OpenAI (Codex & API)Passes with warnings

    Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.

    • Warning

      The name "prior-auth-review-skill" doesn't match its folder "prior-auth". OpenAI's own upload example uses a differently named folder, but the spec it follows says they must match. N4

      Fix: Set name: prior-auth, or rename the folder to prior-auth-review-skill.

  • VS Code & CopilotPasses with warnings

    VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.

    • Warning

      The name "prior-auth-review-skill" doesn't match its folder "prior-auth". VS Code uses the folder name, prior-auth, instead. N4

      Fix: Set name: prior-auth, or rename the folder to prior-auth-review-skill.

SKILL.md

We only show SKILL.md text here when its licence clearly allows it.

Read SKILL.md on GitHub (opens in a new tab)

Files

More from anthropics/healthcare

SkillWhat it can touchPattern checkLicenceUpdated
  • Runs shell commands
  • Bundles scripts
Pattern check: Nothing flaggedNo licence27 Jun 2026
  • Runs shell commands
  • Reaches the network
  • +2 more
Pattern check: Nothing flaggedNo licence15 Jun 2026
  • Touches credentials
  • Runs shell commands
  • +3 more
Pattern check: Nothing flaggedNo licence27 Aug 2026
  • Runs shell commands
  • Names web addresses
  • +1 more
Pattern check: Nothing flaggedNo licence15 Jul 2026
  • Names web addresses
Pattern check: Nothing flaggedNo licence6 Jul 2026
  • Runs shell commands
  • Reaches the network
  • +2 more
Pattern check: Nothing flaggedNo licence15 Jun 2026
All skills in anthropics/healthcare

Other Coding & code review skills

Same category, most repo stars first.

SkillWhat it can touchPattern checkLicenceUpdated
finishing-a-development-branchUse when implementation is complete, all tests pass, and you need to decide how to integrate the work

obra/superpowers

  • Runs shell commands
  • +1 more

Pattern check: Nothing flaggedMITUpdated 12 Aug 2026

  • Runs shell commands
  • Reaches the network
Pattern check: Nothing flaggedMIT12 Aug 2026
  • Reaches the network
Pattern check: Nothing flaggedMIT23 Jul 2026
  • Instructions only
Pattern check: Nothing flaggedMIT11 Aug 2026
  • Instructions only
Pattern check: Nothing flaggedMIT11 Aug 2026
  • Instructions only
Pattern check: Nothing flaggedMIT16 Oct 2026
  • Instructions only
Pattern check: Nothing flaggedMIT8 Oct 2026